Developer Watch: CUVI 0.5 released

Subject: Editorial, General Tech, Graphics Cards | July 26, 2011 - 08:39 PM |
Tagged: gpgpu, Developer Watch, CUVI

Code that can be easily parallelized into many threads have been streaming over to the GPU with many applications and helper libraries taking advantage of CUDA and OpenCL primarily. Thus for developers who wish to utilize the GPU more but are unsure where to start there are more and more options for libraries of functions to call and at least partially embrace their video cards. OpenCV is a library of functions for image manipulation and, while GPU support is ongoing through CUDA, primarily runs on the CPU. CUVIlib, which has just launched their 0.5 release, is a competitor to OpenCV with a strong focus on GPU utilization, performance, and ease of implementation. While OpenCV is licensed as BSD which is about as permissive a license as can be offered, CUVI is not and is based on a proprietary EULA.

Benchmark KLT - CUVILib from TunaCode on Vimeo

Benchmark KLT - OpenCV from TunaCode on Vimeo.

The little plus signs are the computer tracking motion. CUVI (top; 33fps), OpenCV (bottom; 2.5fps)

(Video from CUVIlib)

Despite the proprietary and non-free for commercial use nature of CUVI they advertise large speedups for certain algorithms. For their Kanade-Lucas-Tomasi Feature Tracker algorithm when compared with OpenCV’s implementation they report a three-fold increase in performance with just a GeForce 9800GT installed and 8-13x faster when using a high end computing card such as the Tesla C2050. Their feature page includes footage of two 720p high definition videos undergoing the KLT algorithm with the OpenCV CPU method chugging at 2.5 fps contrasted with CUVI’s GPU-accelerated 33fps. Whether you would prefer to side with OpenCV’s GPU advancements or pay CUVIlib to augment what OpenCV is not good enough for your needs at is up to you, but either future will likely involve the GPU.

Source: CUVIlib

A little something for the audiophile; M-Audio Studiophile Reference Monitor

Subject: General Tech | July 26, 2011 - 06:21 PM |
Tagged: audio, studio quality, audiophile

There are speakers and then there are studio monitors, with the difference being quality.  For most gamers and movie watchers there is no point in picking up a pair of studio quality monitors, not only because of the lack of a discerning ear but also because the audio source is unable to provide the quality these monitors need to perform.  Much as Scotches or wines taste similar to the untrained palate, studio quality speakers are for professionals with professional level needs.  If you are one, or simply want the best possible sound reproduction and are willing to spend $300+ for a pair of monitors then you should check out the M-Audio Studiophile CX5 Active Studio Reference Monitor review at ModSynergy.  With a proper audio card and file as a source these monitors will equal a $1000 pair of monitors and are a great deal for those with the ears to enjoy them.

MSyn_studiophile.jpg

"Today I will be providing a long-term review on a different beast. Today you will be reading the review of one of M-Audio’s latest offerings on the market within their Studiophile lineup, the CX5 High-Resolution Active Studio Reference Monitor. Read on to see how this 90-watt near-field studio monitor performs and holds up. Will this be your next investment?"

Here is some more Tech News from around the web:

Audio Corner

Source: ModSynergy

OCZ wraps both its ARMs around a new SSD controller and gives it a little TLC

Subject: General Tech | July 26, 2011 - 12:03 PM |
Tagged: ssd, ocz, arm, tlc, sata 6Gps, Indilinx Everest

OCZ is never satisfied with the performance of their SSDs in general and their controllers specifically.  After purchasing Indilinx to ensure that their controllers would be of high quality and designed to OCZ's specific needs, they've now been pushing Indilinx to improve on their controllers.  That has lead to Everest, which has a dual core ARM processor and 400MHz DDR3 cache that can support up to 512MB.  The controller is optimized for 8K writes which is perfect for the current flash utilized in SSDs.  OCZ has also optimized the flash memory, developing Triple Level Cell (TLC) which has three layers as opposed to MLC which sports two.  The controller will be backwards compatible, which is a good idea if OCZ wants to license the controller to other manufacturers, which makes sense as Everest should hit 200MT/s as compared to SandForce's current 166MT/s.  There is more that this controller can do, click on over to The Register to read about it.

Holysh.jpg

"OCZ is sampling a new flash controller that gives a picture of future solid state drives.

The company bought Indilinx for its solid state drive (SSD) controller technology in March this year and has now unveiled the Indilinx Everest controller platform.

It has a 6Gbit/s SATA III interface, a dual-core ARM processor and a number of enticing features, such as 3-bit multi-level cell (MLC) support. This is going to be called TLC, for triple-level cell, to distinguish it from today's MLC, which is 2-bit MLC."

Here is some more Tech News from around the web:

Tech Talk

Source: The Register

Apple is da bomb! Vulnerability found in battery circuitry

Subject: Editorial, General Tech | July 25, 2011 - 10:24 PM |
Tagged: Malware, apple

Okay, so the title is more joke than anything else but security researcher Charlie “Safari Charlie” Miller discovered a vulnerability in Apple devices, sort of. This exploit, which appears to not actually be a security flaw and rather just an over-permissive design, allows an attacker to gain access to your battery control using one of two static company-wide passwords. Charlie has discovered many exploits in the past several years on the OSX and iOS platforms. One of the most high profile attacks he discovered involved a data-execution vulnerability in the iPhone’s SMS handling: under certain conditions your iPhone could potentially confuse inbound text messages as code and run it with high permissions.

applebattery.jpg

Malware assaults and battery charges.

(Image from Apple, modified)

So what does having the ability to write to a laptop’s battery firmware mean? Firstly, remember the old advice of “Get a virus? Reinstall your OS!”? Well assuming you actually can perform a clean install without ridiculous hacking (thanks Lion) the battery controller can simply re-infect you if the attacker knows an exploit for your version of OSX. But how does the attacker know your current version of OSX? Well if you are installing from an optical disk they just need to know a Snow Leopard RTM exploit; unless of course you extract Lion from the Mac App Store and clean install using it – assuming the attacker does not know an exploit for Lion or simply just infects the reinstall media if you created it from the infected computer. True, malware is about money so it is highly unlikely that an attacker would go for that narrow of a market of Mac users (already a narrow-enough market to begin with) but the security risk is there if for some reason you are a tempting enough target to spear-phish. Your only truely secure option is removing the battery while performing the OHHHHHHHH.

You know, while working (very temporarily) on the Queen's University Solar Vehicle project I was told that Lithium cells smell like sweet apples when they rupture. I have never experienced it but if true I find it delightfully ironic.

While that would all require knowledge of other exploits in your operating system, there is a more direct problem. If for some reason someone would like to cause damage against your Apple devices they could use this flaw to simply break your batteries. Charlie has bricked nine batteries in his testing but has not even attempted to see whether it would be possible to over-charge a battery into exploding. While it is possible to force the battery controller to create the proper conditions for an explosion there are other, physical, safe guards in place. Then again, batteries have exploded in the past often making highly entertaining Youtube videos and highly unentertaining FOX news clips.

Source: Forbes

Overclocking Llano just makes sense, but the RAM not so much

Subject: General Tech | July 25, 2011 - 03:30 PM |
Tagged: llano, ddr3-1866, a8-3850

Most reviewers made a financial decision when pairing RAM to review AMD's new Llano A8-3850 processor.  Most chose 1333MHz DDR3, since when building a low cost PC most users are going to choose the lower cost as opposed to spending half the budget simply on DDR3.  After seeing significant overclocks produced by a variety of testers, The Tech Report thought it would be interesting to see the impact of high speed RAM on the performance of an A8-3850, especially the graphics portion.   As it turns out, the decision to go with lower cost RAM made a lot of sense as the the graphical performance did not benefit from faster RAM.

TR_llano dimms.jpg

"Will 1866MHz memory make a big difference to the performance of the AMD A8-3850 APU? How does power consumption look without a discrete GPU involved? We aim to find out."

Here are some more Processor articles from around the web:

Processors

Phone in your overclocking, MSI Afterburner App for Android

Subject: General Tech, Graphics Cards, Mobile | July 25, 2011 - 02:58 PM |
Tagged: msi, Android

Are you a hardcore PC user who likes to tweak your computer? Naturally there is an app for you. MSI has launched an application for the Android Marketplace this morning to allow users wishing to monitor and overclock their computers the ability to use their Android-powered smartphone or tablet for that purpose through their wireless network. This version allows you to monitor temperature, voltage, fan speed and adjust clock rates, voltages, and fan speeds.

afterburner.jpg

Let's hope Angry Birds doesn't see this: Some systems' power consumptions are pigs!

MSI Afterburner APP has relatively modest requirements: a tablet or smartphone device running Android 1.6 or higher, a system running Windows XP or later with a discrete graphics card, access to a network with wireless access for the Android device to link into, and Afterburner 2.1.0 or later installed on the PC. Setting up your PC is relatively simple once you have Afterburner installed as you just need to run, not even install, an application “Remote Server” that you can download from the MSI website linked to from the Android Marketplace link. While this application is too new to be rated, it is free and thus there is little reason to not simply try it out yourself.

We know where your Bitcoins went

Subject: General Tech | July 25, 2011 - 01:59 PM |
Tagged: bitcoin

With all the research that Ken did, it turns out that Bitcoin mining will not make you rich overnight and possibly cost you more money to create a bitcoin than you will ever see out of it.  Now, according to a study linked to at Slashdot it seems that one of the big attractions of Bitcoins is not true.  Researchers have found that with enough work and data, Bitcoin purchases are not anonymous.  Anonymity was never a major goal for those who first envisioned Bitcoins but it has been touted as a major feature by those who have been mining and spending coins.  If that is why you are interested in the process of mining maybe it is a better idea to switch to an @home project.

gpu-bitcoin_0.jpg

"Researchers from University College Dublin have conducted an analysis of anonymity on Bitcoin, and found it is not inherently anonymous, and that in many cases, users and their transactions can be identified. They use techniques such as context discovery and flow analysis to investigate and visualize an alleged theft of Bitcoins, which, at the time of the theft, had a market value of approximately half a million U.S. dollars."

Here is some more Tech News from around the web:

Tech Talk

 

Source: Slashdot

Intel MLAA: Matrox had the right idea, wrong everything else

Subject: Editorial, General Tech, Graphics Cards, Processors | July 22, 2011 - 08:20 PM |
Tagged: MLAA, Matrox, Intel

Antialiasing is a difficult task for a computer to accomplish in terms of performance and many efforts have been made over the years to minimize the impact while still keeping as much of the visual appeal as possible. The problem with aliasing is that while pixels are the smallest unit of display on a computer monitor, it is large enough for our eye to see it as a distinct unit. You may however have two objects of two different colors partially occupy the same pixel, who wins? In real life, our eye would see the light from both objects hit the same retina nerve (that is not really how it biologically works but close enough) and it would see some blend between the two colors. Intel has released a whitepaper for their attempt at this problem and it resembles a method that Matrox used almost a decade ago.

MatroxAA.jpg

Matrox's antialiasing method.

(Image from Tom's Hardware)

Looking at the problem of antialiasing, you wish to have multiple bits of information dictate the color of a pixel in the event that two objects of different colors both partially occupy the same pixel. The simplest method of doing that is dividing the pixel up into smaller pixels and then crushing them together to an average which is called Super Sampling. This means you are rendering an image 2x, 4x, or even 16x the resolution you are running at. More methods were discovered including just flagging the edges for antialiasing since that is where aliasing occurs. In the early 2000s, Matrox looked at the problem from an entirely different angle: since the edge is what really matters, we can find the shape of the various edges and see how much area of a pixel gets divided up between each object giving an effect they say is equivalent to 16x MSAA for very little cost. The problem with Matrox’s method: it failed with many cases of shadowing and pixelshaders… and came out in the DirectX 9 era. Suffices to say it did not save Matrox as an elite gaming GPU company.

37399.png

37400.png

Look familiar?

(Both images from Intel Blog)

Intel’s method of antialiasing again looks at the geometry of the image but instead breaks the edges into L shapes to determine the area they enclose. To keep the performance up they do pipelining between the CPU and GPU which keeps the CPU and GPU constantly filled with the target or neighboring frames. In other words, as the GPU lets the CPU perform MLAA, the GPU is busy preparing and drawing the next frame. Of course when I see technology like this I think two things: will this work on architectures with discrete GPUs and will this introduce extra latency between the rendering code and the gameplay code? I would expect that it must as the frame is not even finished let alone drawn to monitor before you fetch the next set of states to be rendered. The question still exists if that effect will be drowned in the rest of the latencies experienced between synchronizing.

AMD and NVIDIA both have their variants of MLAA, the latter of which being called FXAA by NVIDIA's marketing team. Unlike AMD's method, NVIDIA's method must be programmed into the game engine by the development team requiring a little bit of extra work on the developer's part. That said, FXAA found its way into Duke Nukem Forever as well as the upcoming Battlefield 3 among other games so support is there and older games should be easy enough to just compute properly.

37407.png

The flat line is how much time spent on MLAA itself, just a few milliseconds and constant.

(Image from Intel Blog)

Performance-wise the Intel solution performs ridiculously faster than MSAA, is pretty much scene-independent, and should produce results near the 16x mark due to the precision possible with calculating areas. Speculation about latency between render and game loops aside the implementation looks quite sound and allows users with on-processor graphics to not need to waste precious cycles (especially on GPUs that you would see on-processor) with antialiasing and instead use it more on raising other settings including resolution itself while still avoiding jaggies. Conversely, both AMD and NVIDIA's method run on the GPU which should make a little more sense for them as a discrete GPU should not require as much help as a GPU packed into a CPU.

Could Matrox’s last gasp from the gaming market be Intel’s battle cry?

(Registration not required for commenting)

Source: Intel Blog

Mariner 1 is down

Subject: General Tech | July 22, 2011 - 05:49 PM |
Tagged: friday

The biggest mistake you can make, next to admitting you know about computers, is offering tech support to family.   Paying a backyard mechanic in beer, food or both is well ingrained in most peoples mind as is the fact that the repair will not be instantaneous.   Such is not true of the lowly PC tech, not only are you unlikely to be offered anything for your efforts there is usually about a 5 minute time limit for you to finish rebuilding the smoking and infected ruin that once was a loved ones PC.  On the other hand you can't say no to Mom, nor should you go for fancy repairs like you would do for yourself

Not that you can win by keeping things secret of course, nothing will protect you from equipment that shows up dead on your doorstop or works but is just plain recalcitrant.  Sometimes asking for advice before you buy is your best bet, just speculating on unreleased hardware is probably safer.  Even safer would be to just listen to us talk and speculate on hardware in the latest installment of the PC Perspective Podcast ... the last one from the TWiT Cottage.  Next week we should be broadcasting from the new Brick TWiT house.  Then we may be doing something from QuakeCon, don't miss it if you have a chance to go!

 

Bulldozer will be on time, missing CEO or not

Subject: General Tech | July 22, 2011 - 11:42 AM |
Tagged: amd, bulldozer, finance, release

AMD has a lot to happy about today, even if both they and GLOBALFOUNDRIES are one CEO short of a full board.  This time last year AMD was talking up Bulldozer as a product 12 months or more out of market and facing a $43 million loss under “Generally Accepted Accounting Principles”, as Josh explained fully.  Long story short it was money being paid for GF; the unadjusted profit for the quarter was actually $83 million, . This quarter it was a $61 million profit, $70 million non-GAAP, thanks to AMD focusing on keeping the costs down, with a bit of help from the recent release of Llano. 

On the processor side, AMD is pegging the 16-core "Interlagos" Opteron 6200 Bulldozer CPU for servers and the Zambezi FX series will both come out at the same time, at least as far as revenue is concerned.  We may not have them in hand for a while longer than that, but not too long.  Drop by the Register for the full picture.

scroogemcduck.jpg

"The hybrid CPU-GPU chips for mobile PCs gave Advanced Micro Devices some breathing room in the second quarter, but it's going to take continued ramping of these APU processors and an upswing in Opteron server sales to get the company back to the profit levels it should be enjoying during a retooling phase in the IT market – and it looks like AMD and its server partners won't have to wait too much longer."

Here is some more Tech News from around the web:

Tech Talk

Source: The Register